Gradient Dissent: Conversations on AI cover image

Scaling LLMs and Accelerating Adoption with Aidan Gomez at Cohere

Gradient Dissent: Conversations on AI

00:00

How to Fine-Tune a Model to Respond to Commands

A model before it's had this sort of specific human feedback to make it respond to commands? Feels a little bit like schizophrenic. It's hard to get it to do what you want. You're trying to give it instructions and it might break in some very unpredictable way. And then what exactly is happening in that fine-tuning phase with the human feedback? What exactly are you doing?"

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app